© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anger
    -0.31
     Universal
    -0.29
    ×Ļ×Ķ
    -0.27
    Universal
    -0.26
    Program
    -0.25
    universal
    -0.25
    çŃ¾è¯ģ
    -0.24
     universal
    -0.24
     Lansing
    -0.24
     Dangerous
    -0.24
    POSITIVE LOGITS
    çī¹æĸ¯
    0.28
    ä¸Ģå°ı
    0.26
    æĿ¾
    0.25
    ода
    0.25
    /cart
    0.24
    (OP
    0.24
    缺åı£
    0.24
     hạ
    0.24
     лид
    0.23
    (O
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.